Add ngram-mod to spec pipeline: -1.2 tok/s regression

- DFlash+ngram-mod: 17.11 tok/s vs DFlash alone: 18.34 tok/s
- ngram overhead not offset by acceptance rate at current settings
- Keeping in place for now, may tune ngram-mod params later

scripts/serve-llamacpp-dflash.sh

@@ -26,7 +26,7 @@ echo ""
 exec "${SERVER_BIN}" \
     --hf-repo "${TARGET_REPO}" \
     --spec-draft-hf "${DRAFT_REPO}" \
-    --spec-type draft-dflash \
+    --spec-type draft-dflash,ngram-mod \
     --spec-draft-n-max "${DRAFT_N_MAX}" \
     --device ROCm0 \
     --spec-draft-device ROCm0 \